Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to various academic and research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fundamental
    -0.16
    ohl
    -0.15
    uplicates
    -0.15
     spos
    -0.15
    Ī
    -0.14
    olum
    -0.14
    launcher
    -0.14
    egral
    -0.14
    isan
    -0.14
    nám
    -0.14
    POSITIVE LOGITS
    auer
    0.16
    aret
    0.15
    ossip
    0.15
    TI
    0.15
    alet
    0.14
    riott
    0.14
     salv
    0.14
    lesc
    0.14
    ules
    0.14
     leg
    0.14
    Act Density 0.006%

    No Known Activations